Research map / Multi-agent systems and games / Cooperative multi-agent RL
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add experience sharing from other agents (SEAC vs IAC) | IAC · Sparse PP | final return: -0.04 ±0.13 -> 1.93 ±0.13 | Helped |
| add experience sharing (SEAC vs IAC) | IAC · RWARE-(10x20)-4ag | final return: 13.75 ±1.26 -> 23.96 ±1.92 | Helped |
| share experience with separate policies (SEAC) instead of a single shared policy (SNAC) | SNAC · RWARE-(10x20)-4ag | final return: 9.53 ±0.83 -> 23.96 ±1.92 | Helped |
| add experience sharing (SEAC vs IAC) | IAC · LBF-(15x15)-3ag-4f | final return: 0.13 ±0.04 -> 0.43 ±0.09 | Helped |
| add experience sharing (SEAC vs IAC) | IAC · RWARE-(10x11)-4ag | final return: 40.10 ±5.60 -> 45.11 ±2.90 | No clear effect |
| add experience sharing (SEAC vs IAC) | IAC · LBF easiest variant | return | No clear effect |
| add experience sharing (SEAC vs IAC) | IAC · SMAC-3m sparse | final return: -0.13 ±0.01 -> -0.03 ±0.03 | Helped |
| add experience sharing to DQN (shared experience Q-learning) | IQL · sparse-reward tasks | return | Mixed |
| vary experience-sharing weight lambda down toward 0 (ablation) | SEAC · LBF-(15x15)-3ag-4f, RWARE-(10x20) | training return | Mixed |
| SEAC vs MADDPG | MADDPG · PP (sparse) | final return: 2.04 ±0.08 vs 1.93 ±0.13 | No clear effect |
| SEAC vs QMIX | QMIX · LBF-(8x8)-2ag-2f-coop | final return: 0.79 ±0.31 vs 0.64 ±0.08 | No clear effect |
Closest papers by meaning
- Actor-Attention-Critic for Multi-Agent Reinforcement Learning (ICML 2019 · similarity 0.89)
- Off-Policy Actor-Critic with Shared Experience Replay (ICML 2020 · similarity 0.89)
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NeurIPS 2017 · similarity 0.88)
- Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.86)
- Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.